Investigating social alignment via mirroring in a system of interacting language models

By Harvey McGuinness, Tianyu Wang, Carey E. Priebe, Hayden S. Helm. 2024

Subfields: Large Language Models, LLM Agents & Tool Use

Citations in the corpus

• Detecting Perspective Shifts in Multi-agent Systems (2025, unknown): “Multi-agent systems The majority of research on multi-agent generative systems has been in the context of computational sociology and behavioral simulation (Park et al., 2023; McGuinness et al., 2025; Chen et al., 2025a).”
• Gaussian mixture models as a proxy for interacting language models (2025, unknown): “In [6], the authors endow multiple LLMs—each representing a given agent—with RAG databases that are initialized with differing perspectives on a certain type of flower.”
• Toward a digital twin of U.S. Congress (2025, unknown): “Further, simulations of interacting generative agents based on LLMs parameterized by tailored system prompts and data from previous interactions show resemblance to human social systems more generally (21; 12; 18).”